@@ -67,6 +67,7 @@ enum kvm_mode kvm_get_mode(void);
DECLARE_STATIC_KEY_FALSE(userspace_irqchip_in_use);
extern unsigned int kvm_sve_max_vl;
+extern unsigned int kvm_host_sve_max_vl;
int kvm_arm_init_sve(void);
u32 __attribute_const__ kvm_target_cpu(void);
@@ -122,5 +122,6 @@ extern u64 kvm_nvhe_sym(id_aa64isar2_el1_sys_val);
extern u64 kvm_nvhe_sym(id_aa64mmfr0_el1_sys_val);
extern u64 kvm_nvhe_sym(id_aa64mmfr1_el1_sys_val);
extern u64 kvm_nvhe_sym(id_aa64mmfr2_el1_sys_val);
+extern unsigned int kvm_nvhe_sym(kvm_host_sve_max_vl);
#endif /* __ARM64_KVM_HYP_H__ */
@@ -148,15 +148,16 @@ void kvm_arch_vcpu_put_fp(struct kvm_vcpu *vcpu)
local_irq_save(flags);
if (vcpu->arch.fp_state == FP_STATE_GUEST_OWNED) {
- if (vcpu_has_sve(vcpu)) {
- __vcpu_sys_reg(vcpu, ZCR_EL1) = read_sysreg_el1(SYS_ZCR);
-
- /* Restore the VL that was saved when bound to the CPU */
- if (!has_vhe())
- sve_cond_update_zcr_vq(vcpu_sve_max_vq(vcpu) - 1,
- SYS_ZCR_EL1);
- }
-
+ /*
+ * Flush (save and invalidate) the fpsimd/sve state so that if
+ * the host tries to use fpsimd/sve, it's not using stale data
+ * from the guest.
+ *
+ * Flushing the state sets the TIF_FOREIGN_FPSTATE bit for the
+ * context unconditionally, in both nVHE and VHE. This allows
+ * the kernel to restore the fpsimd/sve state, including ZCR_EL1
+ * when needed.
+ */
fpsimd_save_and_flush_cpu_state();
}
@@ -44,6 +44,11 @@ alternative_if ARM64_HAS_RAS_EXTN
alternative_else_nop_endif
mrs x1, isr_el1
cbz x1, 1f
+
+ // Ensure that __guest_enter() always provides a context
+ // synchronization event so that callers don't need ISBs for anything
+ // that would usually be synchonized by the ERET.
+ isb
mov x0, #ARM_EXCEPTION_IRQ
ret
@@ -167,6 +167,61 @@ static inline void __hyp_sve_restore_guest(struct kvm_vcpu *vcpu)
write_sysreg_el1(__vcpu_sys_reg(vcpu, ZCR_EL1), SYS_ZCR);
}
+static inline void fpsimd_lazy_switch_to_guest(struct kvm_vcpu *vcpu)
+{
+ u64 zcr_el1, zcr_el2;
+
+ if (!guest_owns_fp_regs(vcpu))
+ return;
+
+ if (vcpu_has_sve(vcpu)) {
+ zcr_el2 = vcpu_sve_max_vq(vcpu) - 1;
+
+ write_sysreg_el2(zcr_el2, SYS_ZCR);
+
+ zcr_el1 = __vcpu_sys_reg(vcpu, ZCR_EL1);
+ write_sysreg_el1(zcr_el1, SYS_ZCR);
+ }
+}
+
+static inline void fpsimd_lazy_switch_to_host(struct kvm_vcpu *vcpu)
+{
+ u64 zcr_el1, zcr_el2;
+
+ if (!guest_owns_fp_regs(vcpu))
+ return;
+
+ /*
+ * When the guest owns the FP regs, we know that guest+hyp traps for
+ * any FPSIMD/SVE/SME features exposed to the guest have been disabled
+ * by either fpsimd_lazy_switch_to_guest() or kvm_hyp_handle_fpsimd()
+ * prior to __guest_entry(). As __guest_entry() guarantees a context
+ * synchronization event, we don't need an ISB here to avoid taking
+ * traps for anything that was exposed to the guest.
+ */
+ if (vcpu_has_sve(vcpu)) {
+ zcr_el1 = read_sysreg_el1(SYS_ZCR);
+ __vcpu_sys_reg(vcpu, ZCR_EL1) = zcr_el1;
+
+ /*
+ * The guest's state is always saved using the guest's max VL.
+ * Ensure that the host has the guest's max VL active such that
+ * the host can save the guest's state lazily, but don't
+ * artificially restrict the host to the guest's max VL.
+ */
+ if (has_vhe()) {
+ zcr_el2 = vcpu_sve_max_vq(vcpu) - 1;
+ write_sysreg_el2(zcr_el2, SYS_ZCR);
+ } else {
+ zcr_el2 = sve_vq_from_vl(kvm_host_sve_max_vl) - 1;
+ write_sysreg_el2(zcr_el2, SYS_ZCR);
+
+ zcr_el1 = vcpu_sve_max_vq(vcpu) - 1;
+ write_sysreg_el1(zcr_el1, SYS_ZCR);
+ }
+ }
+}
+
/*
* We trap the first access to the FP/SIMD to save the host context and
* restore the guest context lazily.
@@ -5,6 +5,7 @@
*/
#include <hyp/adjust_pc.h>
+#include <hyp/switch.h>
#include <asm/pgtable-types.h>
#include <asm/kvm_asm.h>
@@ -25,7 +26,9 @@ static void handle___kvm_vcpu_run(struct kvm_cpu_context *host_ctxt)
{
DECLARE_REG(struct kvm_vcpu *, vcpu, host_ctxt, 1);
+ fpsimd_lazy_switch_to_guest(kern_hyp_va(vcpu));
cpu_reg(host_ctxt, 1) = __kvm_vcpu_run(kern_hyp_va(vcpu));
+ fpsimd_lazy_switch_to_host(kern_hyp_va(vcpu));
}
static void handle___kvm_adjust_pc(struct kvm_cpu_context *host_ctxt)
@@ -285,11 +288,6 @@ void handle_trap(struct kvm_cpu_context *host_ctxt)
case ESR_ELx_EC_SMC64:
handle_host_smc(host_ctxt);
break;
- case ESR_ELx_EC_SVE:
- sysreg_clear_set(cptr_el2, CPTR_EL2_TZ, 0);
- isb();
- sve_cond_update_zcr_vq(ZCR_ELx_LEN_MASK, SYS_ZCR_EL2);
- break;
case ESR_ELx_EC_IABT_LOW:
case ESR_ELx_EC_DABT_LOW:
handle_host_mem_abort(host_ctxt);
@@ -9,6 +9,8 @@
#include <nvhe/fixed_config.h>
#include <nvhe/trap_handler.h>
+unsigned int kvm_host_sve_max_vl;
+
/*
* Set trap register values based on features in ID_AA64PFR0.
*/
@@ -40,6 +40,9 @@ static void __activate_cptr_traps(struct kvm_vcpu *vcpu)
{
u64 val = CPTR_EL2_TAM; /* Same bit irrespective of E2H */
+ if (!guest_owns_fp_regs(vcpu))
+ __activate_traps_fpsimd32(vcpu);
+
/* !hVHE case upstream */
if (1) {
val |= CPTR_EL2_TTA | CPTR_NVHE_EL2_RES1;
@@ -55,12 +58,24 @@ static void __activate_cptr_traps(struct kvm_vcpu *vcpu)
if (!guest_owns_fp_regs(vcpu))
val |= CPTR_EL2_TFP;
+
+ write_sysreg(val, cptr_el2);
}
+}
- if (!guest_owns_fp_regs(vcpu))
- __activate_traps_fpsimd32(vcpu);
+static void __deactivate_cptr_traps(struct kvm_vcpu *vcpu)
+{
+ /* !hVHE case upstream */
+ if (1) {
+ u64 val = CPTR_NVHE_EL2_RES1;
- write_sysreg(val, cptr_el2);
+ if (!cpus_have_final_cap(ARM64_SVE))
+ val |= CPTR_EL2_TZ;
+ if (!cpus_have_final_cap(ARM64_SME))
+ val |= CPTR_EL2_TSM;
+
+ write_sysreg(val, cptr_el2);
+ }
}
static void __activate_traps(struct kvm_vcpu *vcpu)
@@ -89,7 +104,6 @@ static void __activate_traps(struct kvm_vcpu *vcpu)
static void __deactivate_traps(struct kvm_vcpu *vcpu)
{
extern char __kvm_hyp_host_vector[];
- u64 cptr;
___deactivate_traps(vcpu);
@@ -114,13 +128,7 @@ static void __deactivate_traps(struct kvm_vcpu *vcpu)
write_sysreg(this_cpu_ptr(&kvm_init_params)->hcr_el2, hcr_el2);
- cptr = CPTR_EL2_DEFAULT;
- if (vcpu_has_sve(vcpu) && (vcpu->arch.fp_state == FP_STATE_GUEST_OWNED))
- cptr |= CPTR_EL2_TZ;
- if (cpus_have_final_cap(ARM64_SME))
- cptr &= ~CPTR_EL2_TSM;
-
- write_sysreg(cptr, cptr_el2);
+ __deactivate_cptr_traps(vcpu);
write_sysreg(__kvm_hyp_host_vector, vbar_el2);
}
@@ -134,6 +134,8 @@ static int __kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu)
sysreg_save_host_state_vhe(host_ctxt);
+ fpsimd_lazy_switch_to_guest(vcpu);
+
/*
* ARM erratum 1165522 requires us to configure both stage 1 and
* stage 2 translation for the guest context before we clear
@@ -164,6 +166,8 @@ static int __kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu)
__deactivate_traps(vcpu);
+ fpsimd_lazy_switch_to_host(vcpu);
+
sysreg_restore_host_state_vhe(host_ctxt);
if (vcpu->arch.fp_state == FP_STATE_GUEST_OWNED)
@@ -42,11 +42,14 @@ static u32 kvm_ipa_limit;
PSR_AA32_I_BIT | PSR_AA32_F_BIT)
unsigned int kvm_sve_max_vl;
+unsigned int kvm_host_sve_max_vl;
int kvm_arm_init_sve(void)
{
if (system_supports_sve()) {
kvm_sve_max_vl = sve_max_virtualisable_vl();
+ kvm_host_sve_max_vl = sve_max_vl();
+ kvm_nvhe_sym(kvm_host_sve_max_vl) = kvm_host_sve_max_vl;
/*
* The get_sve_reg()/set_sve_reg() ioctl interface will need